PulseAugur
实时 13:12:25

New AEGIS benchmark reveals AI image forensics lag behind generative advances

Researchers have introduced AEGIS, a new benchmark designed to evaluate the forensic analysis of AI-generated academic images. This benchmark addresses domain-specific complexity across seven academic categories and incorporates diverse forgery simulations from 25 generative models. AEGIS also employs a multi-dimensional forensic evaluation, assessing detection, reasoning, and localization to reveal limitations in current academic image forensics. AI

影响 This benchmark highlights the growing challenge of detecting AI-generated academic images and the lag in forensic capabilities.

排序理由 The cluster describes a new academic benchmark paper.

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

New AEGIS benchmark reveals AI image forensics lag behind generative advances

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haih ·

    AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images

    arXiv:2604.28177v1 Announce Type: new Abstract: We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic c…

  2. arXiv cs.CV TIER_1 English(EN) · Haihong E ·

    AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images

    We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposin…